{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:20:24Z","timestamp":1781972424235,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC (National Natural Science Foundation of China)","award":["62002366"],"award-info":[{"award-number":["62002366"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545053","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Mentha: Enabling Sparse-Packing Computation on Systolic Arrays"],"prefix":"10.1145","author":[{"given":"Minjin","family":"Tang","sequence":"first","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasong","family":"Cao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchao","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Fei","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Guo","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Evolutionary Mapping Techniques for Systolic Computing System. Deep Learning and Parallel Computing Environment for Bioengineering Systems","author":"Bagavathi C","year":"2019","unstructured":"C Bagavathi and O Saraniya. 2019. Evolutionary Mapping Techniques for Systolic Computing System. Deep Learning and Parallel Computing Environment for Bioengineering Systems (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293898"},{"key":"e_1_3_2_1_3_1","unstructured":"NVIDIA Corporation. 2012. CUDA CUSPARSE Library."},{"key":"e_1_3_2_1_4_1","volume-title":"EMNLP\/IJCNLP (1)","author":"Cui Baiyun","unstructured":"Baiyun Cui, Yingming Li, Ming Chen, and Zhongfei Zhang. 2019. Fine-tune BERT with Sparse Self-Attention Mechanism. In EMNLP\/IJCNLP (1). Association for Computational Linguistics, 3546\u20133551."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_6_1","unstructured":"Tim Dettmers and Luke Zettlemoyer. 2019. Sparse Networks from Scratch: Faster Training without Losing Performance. CoRR abs\/1907.04840(2019)."},{"key":"e_1_3_2_1_7_1","unstructured":"Utku Evci Trevor Gale Jacob Menick Pablo\u00a0Samuel Castro and Erich Elsen. 2020. Rigging the Lottery: Making All Tickets Winners. In ICML(Proceedings of Machine Learning Research Vol.\u00a0119). PMLR 2943\u20132952."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00070"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392751"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kartik Hegde Hadi\u00a0Asghari Moghaddam Michael Pellauer Neal\u00a0Clayton Crago Aamer Jaleel Edgar Solomonik Joel\u00a0S. Emer and Christopher\u00a0W. Fletcher. 2019. ExTensor: An Accelerator for Sparse Tensor Algebra. In MICRO. ACM 319\u2013333.","DOI":"10.1145\/3352460.3358275"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Changwan Hong Aravind Sukumaran-Rajam Israt Nisa Kunal Singh and P. Sadayappan. 2019. Adaptive sparse tiling for sparse matrix multiplication. In PPoPP. ACM 300\u2013314.","DOI":"10.1145\/3293883.3295712"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_16_1","volume-title":"Why Systolic Architectures?Computer 15, 1","author":"Kung T.","year":"1982","unstructured":"H.\u00a0T. Kung. 1982. Why Systolic Architectures?Computer 15, 1 (1982), 37\u201346."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"H.\u00a0T. Kung Bradley McDanel and Sai\u00a0Qian Zhang. 2019. Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization. In ASPLOS. ACM 821\u2013834.","DOI":"10.1145\/3297858.3304028"},{"key":"e_1_3_2_1_18_1","unstructured":"S\u00fcreyya\u00a0Emre Kurt Aravind Sukumaran-Rajam Fabrice Rastello and P. Sadayappan. 2020. Efficient tiled sparse matrix multiplication through matrix signatures. In SC. IEEE\/ACM 87."},{"key":"e_1_3_2_1_19_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Lee Namhoon","year":"2019","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip H.\u00a0S. Torr. 2019. Snip: single-Shot Network Pruning based on Connection sensitivity. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=B1VZqjAcYX"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012212"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00049"},{"key":"e_1_3_2_1_22_1","volume-title":"Sanger: A Co-Design Framework for Enabling Sparse Attention using Reconfigurable Architecture. In MICRO. ACM, 977\u2013991.","author":"Lu Liqiang","year":"2021","unstructured":"Liqiang Lu, Yicheng Jin, Hangrui Bi, Zizhang Luo, Peng Li, Tao Wang, and Yun Liang. 2021. Sanger: A Co-Design Framework for Enabling Sparse Attention using Reconfigurable Architecture. In MICRO. ACM, 977\u2013991."},{"key":"e_1_3_2_1_23_1","volume-title":"TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training","author":"Mahmoud Mostafa","unstructured":"Mostafa Mahmoud, Isak Edo, Ali\u00a0Hadi Zadeh, Omar\u00a0Mohamed Awad, Gennady Pekhimenko, Jorge Albericio, and Andreas Moshovos. 2020. TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training. In MICRO. IEEE, 781\u2013795."},{"key":"e_1_3_2_1_24_1","volume-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications 9 (06","author":"Mocanu Decebal","year":"2018","unstructured":"Decebal Mocanu, Elena Mocanu, Peter Stone, Phuong Nguyen, Madeleine Gibescu, and Antonio Liotta. 2018. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications 9 (06 2018)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 4646\u20134655."},{"key":"e_1_3_2_1_26_1","volume-title":"OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator. In IEEE International Symposium on High Performance Computer Architecture, HPCA 2018","author":"Pal Subhankar","year":"2018","unstructured":"Subhankar Pal, Jonathan Beaumont, Dong-Hyeon Park, Aporva Amarnath, Siying Feng, Chaitali Chakrabarti, Hun-Seok Kim, David\u00a0T. Blaauw, Trevor\u00a0N. Mudge, and Ronald\u00a0G. Dreslinski. 2018. OuterSPACE: An Outer Product Based Sparse Matrix Multiplication Accelerator. In IEEE International Symposium on High Performance Computer Architecture, HPCA 2018, Vienna, Austria, February 24-28, 2018. IEEE Computer Society, 724\u2013736."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_2_1_28_1","volume-title":"SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training. In HPCA.","author":"Qin Eric","year":"2020","unstructured":"Eric Qin, Ananda Samajdar, Hyoukjun Kwon, Vineet Nadella, Sudarshan Srinivasan, Dipankar Das, Bharat Kaul, and Tushar Krishna. 2020. SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training. In HPCA."},{"key":"e_1_3_2_1_29_1","volume-title":"An Accelerator for Sparse Convolutional Neural Networks Leveraging Systolic General Matrix-Matrix Multiplication. ACM Transactions on Architecture and Code Optimization (04","author":"Soltaniyeh Mohammadreza","year":"2022","unstructured":"Mohammadreza Soltaniyeh, Richard Martin, and Santosh Nagarakatte. 2022. An Accelerator for Sparse Convolutional Neural Networks Leveraging Systolic General Matrix-Matrix Multiplication. ACM Transactions on Architecture and Code Optimization (04 2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"MatRaptor: A Sparse-Sparse Matrix Multiplication Accelerator Based on Row-Wise Product. In 53rd Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 2020","author":"Srivastava Nitish\u00a0Kumar","year":"2020","unstructured":"Nitish\u00a0Kumar Srivastava, Hanchen Jin, Jie Liu, David\u00a0H. Albonesi, and Zhiru Zhang. 2020. MatRaptor: A Sparse-Sparse Matrix Multiplication Accelerator Based on Row-Wise Product. In 53rd Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 2020, Athens, Greece, October 17-21, 2020. IEEE, 766\u2013780."},{"key":"e_1_3_2_1_31_1","volume-title":"ASAP7 predictive design kit development and cell design technology co-optimization: Invited paper","author":"Vashishtha Vinay","unstructured":"Vinay Vashishtha, Manoj Vangala, and Lawrence\u00a0T. Clark. 2017. ASAP7 predictive design kit development and cell design technology co-optimization: Invited paper. In ICCAD. IEEE, 992\u2013998."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00064"},{"key":"e_1_3_2_1_33_1","volume-title":"SpArch: Efficient Architecture for Sparse Matrix Multiplication","author":"Zhang Zhekai","unstructured":"Zhekai Zhang, Hanrui Wang, Song Han, and William\u00a0J. Dally. 2020. SpArch: Efficient Architecture for Sparse Matrix Multiplication. In HPCA. IEEE, 261\u2013274."},{"key":"e_1_3_2_1_34_1","unstructured":"Guangxiang Zhao Junyang Lin Zhiyuan Zhang Xuancheng Ren Qi Su and Xu Sun. 2019. Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection. CoRR abs\/1912.11637(2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Cambricon-S: Addressing Irregularity in Sparse Neural Networks through A Cooperative Software\/Hardware Approach","author":"Zhou Xuda","unstructured":"Xuda Zhou, Zidong Du, Qi Guo, Shaoli Liu, Chengsi Liu, Chao Wang, Xuehai Zhou, Ling Li, Tianshi Chen, and Yunji Chen. 2018. Cambricon-S: Addressing Irregularity in Sparse Neural Networks through A Cooperative Software\/Hardware Approach. In MICRO. IEEE Computer Society, 15\u201328."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Maohua Zhu Tao Zhang Zhenyu Gu and Yuan Xie. 2019. Sparse Tensor Core: Algorithm and Hardware Co-Design for Vector-wise Sparse Neural Networks on Modern GPUs. In MICRO. ACM 359\u2013371.","DOI":"10.1145\/3352460.3358269"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545053","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:44Z","timestamp":1750186964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545053"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":36,"alternative-id":["10.1145\/3545008.3545053","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545053","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}